Author
Name Claire Descombes
Affiliation Universitätsklinik fßr Neurochirurgie, Inselspital Bern
Degree MSc Statistics and Data Science, University of Bern
Contact claire.descombes@insel.ch

The reference material for this course, as well as some useful literature to deepen your knowledge of R, can be found at the bottom of the page.

1 Importing data

1.1 Working directory

When you get a file from somewhere on your computer (e.g. a dataset), you can either

  • have it in your R working directory (see below), in which case you don’t need to specify the full path to the file when you import it,
  • or you can get files in different folders, by always specifying the full path.

The advantage of putting the files in the folder that contains your script and is set as the working directory is that you can easily move the folder around on your computer without getting any problems with your script: just set the working directory to your source file every time you open it, and you’ll be fine.

# Example
setwd("~/path/to/your/folder/")
data <- read.csv("testdata.csv")

The advantage of always giving the full path to a file is that you can get data in different folders on your computer, avoiding things like copying the source data in every folder where you have a corresponding script.

# Example
data <- read.csv("~/path/to/your/folder/testdata.csv")

Working directory

To tell R which folder you are working in (e.g., where your data is stored), you have several options:

  • Go to Session > Set Working Directory > Choose Directory and select your folder manually.
  • Use setwd("path/to/your/folder") in your script.
  • Or, the most convenient for script-based work: go to Session > Set Working Directory > To Source File Location to automatically set the working directory to the location of your script.

💡 Tip: To avoid file path errors and keep your project organized, it’s best to store your script and data files in the same folder — or at least place your data files in a subfolder like data_sets within your project directory. Then, set that folder as your working directory in R. This ensures that your code can reliably find and save your files.

getwd()                         # Displays the current working directory
setwd("~/path/to/your/folder")  # Sets the working directory

1.2 Import CSV and xlsx data

We will first look at how to import a CSV file into R as a data frame.

CSV stands for Comma-Separated Values. In a .csv file, the values are stored as plain text, separated by commas. This is a simple and widely used format for storing tabular data.

After setting your working directory or determining the path to your CSV file, you can use the read.csv() function to import the data. This will create a data frame, which is one of the most commonly used structures in R for handling datasets.

# Import a CSV file into a data frame
dataset <- read.csv("~/path/to/your/folder/data.csv")

💡 I recommend using data frames — they are generally easier to work with than matrices, especially for beginners.

Another widely used data format is the Excel file (.xlsx). For these, you can use the readxl package to import the data:

# Load the readxl package (after installing it)
library(readxl)

# Read the first sheet of an Excel file
dataset <- read_excel("~/path/to/your/folder/data.xlsx")

⚠️ Note: If your file is actually a CSV but mistakenly has a .xlsx extension, you should rename it to .csv and use read.csv() instead. Mixing up formats can lead to import errors.

1.2.1 Load the NHANES data sets

Let us now look at real data frames to learn how to call or modify their elements. To do this, we will use multiple health data sets from the National Health and Nutrition Examination (NHANES) Survey from 2011-2012. The survey assessed overall health and nutrition of adults and children in the United States and was conducted by the National Center for Health Statistics (NCHS). The data sets can be found in the data_sets folder.

Dataset NHANES Code Description CSV File
Demographics DEMO_G Age, sex, race/ethnicity, income, education DEMO_G.csv
Blood Pressure BPX_G Systolic/diastolic blood pressure, number of readings BPX_G.csv
Body Measures BMX_G Height, weight, BMI, waist circumference BMX_G.csv
Smoking Questionnaire SMQ_G Smoking habits, exposure to secondhand smoke SMQ_G.csv 
# Load the necessary CSV files into data frames
demo <- read.csv("/home/claire/Documents/GitHub/rforphysicians/data_sets/DEMO_G.csv") # Demographics (cycle G = 2011–2012)
bpx  <- read.csv("/home/claire/Documents/GitHub/rforphysicians/data_sets/BPX_G.csv") # Blood pressure
bmx  <- read.csv("/home/claire/Documents/GitHub/rforphysicians/data_sets/BMX_G.csv") # Body measures
smq  <- read.csv("/home/claire/Documents/GitHub/rforphysicians/data_sets/SMQ_G.csv") # Smoking questionnaire

💡 The codebook for each data set can be accessed either on the NCHS website or directly in R using the function nhanesCodebook(nh_table, colname) from the package nhanesA (which I used to download the data). You’ll also find a summary of key variables from each data set at the end of this chapter.

1.3 Exercises

✏️ Exercise on the NHANES data sets n°1: import the demo, bpx, bmx and smq data sets from the data_sets folder into R.

2 Handling data

2.1 Base R vs tidyverse

Base R, without any additional packages, already provides many functions that are very handy for data handling. However, some contributed packages make data preparation much easier and more readable.

I’ll introduce two such packages here, before diving into concrete data handling examples. Both are part of a larger and very powerful collection of packages for data science called the tidyverse, which I use for nearly all my analyses.

2.1.1 The pipe

One of the most downloaded contributed extension packages of all times is magrittr. It provides a very useful operator, the forward pipe operator %>%, which passes the object on its left as the first argument to the function on its right. This is much easier to understand with an example.

# The easiest way to get magrittr is to install the whole tidyverse
install.packages("tidyverse")
# Once installed, a package has to be loaded to be used
library(tidyverse)
library(tidyverse)

# Let's do the same operation twice: once using the pipe, once without

# No pipe:
str(c(1,2,3,4))
##  num [1:4] 1 2 3 4
# With pipe:
c(1,2,3,4) %>%
  str()
##  num [1:4] 1 2 3 4
# Not too exciting yet, but consider a more complex case:
summary(log(sqrt(na.omit(c(1, 4, NA, 16, 25)))))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.5199  1.0397  0.9222  1.4421  1.6094
# With the pipe, we can rewrite this more readably:
c(1, 4, NA, 16, 25) %>%
  na.omit() %>%
  sqrt() %>%
  log() %>%
  summary()
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.5199  1.0397  0.9222  1.4421  1.6094

The pipe helps turn nested function calls into a sequence of simpler, linear steps. This makes code easier to read, write, and debug. The pipe becomes especially powerful when used with functions from the dplyr package for data manipulation.

2.1.2 dplyr

Another helpful R package is dplyr. It is a grammar of data manipulation, providing a consistent set of verbs that helps solve the most common data manipulation challenges.

Let’s illustrate this with a simple example. Our goal: Group the cars dataset (contained in base R) by speed groups (e.g. low/medium/high), and for each group, compute (1) the average stopping distance and (2) the number of observations.

# Base R (no dplyr, no pipe)

cars$speed_group <- cut(cars$speed, breaks = c(0, 10, 20, 30), 
                        labels = c("Low", "Medium", "High"))

avg_dist <- aggregate(dist ~ speed_group, data = cars, mean)
n_obs <- aggregate(dist ~ speed_group, data = cars, length)
names(n_obs)[2] <- "n"

summary_df <- merge(avg_dist, n_obs, by = "speed_group")
summary_df
# With dplyr, no pipe:

cars <- mutate(cars, speed_group = cut(speed, breaks = c(0, 10, 20, 30), labels = c("Low", "Medium", "High")))

summary_df <- summarise(group_by(cars, speed_group),
                        avg_dist = mean(dist),
                        n = n())
summary_df
# With dplyr and the pipe
cars %>%
  mutate(speed_group = cut(speed, breaks = c(0, 10, 20, 30), 
                           labels = c("Low", "Medium","High"))) %>%
  group_by(speed_group) %>%
  summarise(
    avg_dist = mean(dist),
    n = n()
  )

💡 cut(x, ...) divides the range of x into intervals (the breaks) and codes the values in x according to which interval they fall. labels are the levels of the resulting category. If labels = FALSE, simple integer codes are returned instead of a factor.

As you can see, using dplyr and the pipe can make your life much easier.

In the following chapter, we’ll use both base R and tidyverse functions without always noting which package they belong to. If you’re ever unsure, you can check the top-left corner of the function’s help page.

2.2 Accessing elements in data frames

Being able to access elements in a data frame is essential when working with data. Here are some common methods to select specific elements, rows, or columns.

# Look at the first respectively last few rows
head(demo)
tail(demo)
# Select columns by name
demo[, c("RIDAGEYR", "RIAGENDR")]  # Selecting age in years and gender
vars <- c("RIDAGEYR", "RIAGENDR")
demo[, vars]  # Alternative using variable `vars`
# Select elements by position
demo[1, 1]  # Access the first element of the first column (the respondent sequence number of the 1st participant)
## [1] 62161
ind_mat <- cbind(c(1, 3, 5), c(2, 4, 6))
demo[ind_mat]  # Access rows and columns using multiple indices
## [1] "NHANES 2011-2012 public release" "Male"                           
## [3] NA
# Select rows based on a condition
head(demo[, "RIDAGEYR"] > 50)  # Logical condition for age greater than 50
## [1] FALSE FALSE FALSE FALSE FALSE FALSE
head(!(demo[, "DMDHHSIZ"] > 3))  # Logical negation for total number of people in the household not greater than 3
## [1] FALSE FALSE FALSE FALSE FALSE FALSE
demo[demo[, "RIDAGEYR"] > 50, ]  # Rows where age > 50
demo[demo[, "DMDHHSIZ"] < 3, ]  # Rows where total number of people in the household greater than 3
demo[demo[, "DMDHHSIZ"] >= 3, ]  # Rows where total number of people in the household greater or equal 3
# Combine logical vectors using "&" (AND), "|" (OR), and "!" (NOT)
demo[(demo[, "RIDAGEYR"] > 50 & demo[, "RIAGENDR"] == "Female"), ]  # Both conditions must be true
demo[(demo[, "DMDHHSIZ"] < 3 | demo[, "RIAGENDR"] == "Male"), ]  # One condition must be true

💡 To inspect one column, you can also use the dollar $ symbol to access a column as a vector.

head(demo$RIDAGEYR)  # Returns the age column as a vector
## [1] 22  3 14 44 14  9

💡 You can use the brackets [] to select specific rows and columns. Since data frames are bi-dimensional, the first index refers to rows and the second to columns. To select a particular column, you can omit the row index. To select a particular row, omit the column index.

head(demo[, "RIDAGEYR"])  # All rows in the age column
## [1] 22  3 14 44 14  9
demo[1, ]  # Row 1 (all columns)

2.3 Basic descriptive statistics

R makes it simple to compute basic descriptive statistics for exploring your dataset. Below are a few useful examples.

2.3.1 Central tendency: mean and median

mean(demo$RIDAGEYR, na.rm = TRUE)                 # Average (mean) age of participants
## [1] 31.40262
median(demo$DMDHHSIZ, na.rm = TRUE)               # Median household size
## [1] 4

💡 The na.rm argument in those functions allows for ignoring the NA values.

2.3.2 Dispersion: standard deviation, min, max, and range

sd(demo$RIDAGEYR, na.rm = TRUE)                     # Standard deviation of age
## [1] 24.57899
range(demo$DMDHHSZA, na.rm = TRUE)                  # Range of number of young children
## [1] 0 3
min(demo$DMDHRAGE, na.rm = TRUE)                    # Minimum age of household reference person
## [1] 18
max(demo$DMDHRAGE, na.rm = TRUE)                    # Maximum age of household reference person
## [1] 80

2.3.3 Frequency tables and proportions

table(demo$RIAGENDR)                                # Gender distribution
## 
## Female   Male 
##   4900   4856
table(demo$DMDHRMAR)                                # Marital status of household reference person
## 
##            Divorced          Don't Know Living with partner             Married 
##                 816                   8                 876                5282 
##       Never married             Refused           Separated             Widowed 
##                1539                  82                 436                 581
table(demo$AIALANGA)                                # Language of interview
## 
## Asian languages         English         Spanish 
##              95            5192             467
prop.table(table(demo$AIALANGA))                    # Proportional distribution of interview languages
## 
## Asian languages         English         Spanish 
##      0.01651025      0.90232881      0.08116093

2.3.4 Group-wise summaries

aggregate(DMDHRAGE ~ DMDHRMAR, data = demo, FUN = mean, na.rm = TRUE)   # Mean age of household reference person by marital status
aggregate(DMDHHSIZ ~ DMDHRGND, data = demo, FUN = median, na.rm = TRUE) # Median household size by gender of reference person

2.3.5 Full overview

summary(demo)[,1:5] # only for the first 5 variables
##       SEQN         SDDSRVYR           RIDSTATR           RIAGENDR        
##  Min.   :62161   Length:9756        Length:9756        Length:9756       
##  1st Qu.:64600   Class :character   Class :character   Class :character  
##  Median :67038   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :67038                                                           
##  3rd Qu.:69477                                                           
##  Max.   :71916                                                           
##                                                                          
##     RIDAGEYR   
##  Min.   : 0.0  
##  1st Qu.: 9.0  
##  Median :26.0  
##  Mean   :31.4  
##  3rd Qu.:52.0  
##  Max.   :80.0  
##

2.4 Modifying elements in data frames

Now, let us assume we want to modify/add/remove one or multiple entries/rows/columns in our data frame. The brackets really come in handy now. In this setting, I recommend defining a new data frame before modifying the original one.

Some examples follow.

# Modify one entry:
demo_mod <- demo  # Create a copy to avoid modifying the original data set
demo_mod[1, 1:5]
demo_mod[1, "RIAGENDR"] <- 'Female' # Change gender of the first participant
demo_mod[1, 1:5]
# Modify multiple entries based on a condition:
demo_mod[1:10, 1:5]
demo_mod[!is.na(demo_mod$RIDAGEYR) & demo_mod$RIDAGEYR < 18, ]$RIDAGEYR <- 18  # Set minimum age to 18
demo_mod[1:10, 1:5]

2.5 Dealing with NAs

Handling missing data (NAs) is a common task in data analysis. Before deciding how to treat them, it’s important to understand where and how often they occur.

colSums(is.na(demo))              # Number of NAs per column
##     SEQN SDDSRVYR RIDSTATR RIAGENDR RIDAGEYR RIDAGEMN RIDRETH1 RIDRETH3 
##        0        0        0        0        0     9130        0        0 
## RIDEXMON RIDEXAGY RIDEXAGM DMQMILIZ  DMQADFC DMDBORN4 DMDCITZN DMDYRSUS 
##      418     6338     5747     3749     9205        0        5     7683 
## DMDEDUC3 DMDEDUC2 DMDMARTL RIDEXPRG  SIALANG SIAPROXY SIAINTRP  FIALANG 
##     7157     4196     4196     8548        0        6        0      105 
## FIAPROXY FIAINTRP  MIALANG MIAPROXY MIAINTRP AIALANGA WTINT2YR WTMEC2YR 
##      105      105     3043     3043     3043     4002        0        0 
##  SDMVPSU SDMVSTRA INDHHIN2 INDFMIN2 INDFMPIR DMDHHSIZ DMDFMSIZ DMDHHSZA 
##        0        0       81       51      840        0        0        0 
## DMDHHSZB DMDHHSZE DMDHRGND DMDHRAGE DMDHRBR4 DMDHREDU DMDHRMAR DMDHSEDU 
##        0        0        0        0      365      362      136     4881
sum(complete.cases(demo))         # Number of rows without any NAs
## [1] 0

💡 is.na() returns a logical matrix where TRUE indicates a missing value (NA) and FALSE indicates a non-missing value. colSums() takes this logical matrix and sums up the TRUE values (which are treated as 1), giving you the count of missing values for each column.

💡 complete.cases() returns a logical vector: TRUE if a row has no missing values, and FALSE otherwise. Using sum(complete.cases(...)) counts the number of rows with no missing data.

One way to handle missing data is to remove rows containing NAs for the variable(s) you are interested in. This can be appropriate in some cases, but it should be done with care, as it may introduce bias or reduce sample size. We’ll discuss this further in chapter 4.

# Remove rows with any missing values in the DMDHRMAR column
demo_DMDHRMAR <- demo[!is.na(demo$DMDHRMAR), ]

# Check for missing values
sum(is.na(demo_DMDHRMAR$DMDHRMAR))
## [1] 0

You can remove all rows with missing values across any of the columns in the dataset using the function na.omit().

# Remove rows with missing values in any column
demo_no_na <- na.omit(demo)

# Check the resulting data frame and its structure
head(demo_no_na)

💡 For our demo data set, this removes all the rows! Another reminder to be very careful when removing NA values.

2.6 Exercises

✏️ Exercise on the NHANES data sets n°2: inspect the structure of the demo data set, look at different entries, get familiar with those commands.

✏️ Exercise on the NHANES data sets n°3: generate a new data frame selecting only the female patients that are above 18 years old and that took the interview in Spanish.

3 Combining data

In practice, data is often spread across multiple data frames that need to be combined. Depending on the structure and goal, there are different ways to combine data frames:

3.1 Column binding with cbind()

Use cbind() to add columns side-by-side. The data frames must have the same number of rows.

# Extract one column from demo to create an additional data frame with the same number of rows
extra_info <- demo$RIDRETH1

# Combine using cbind
combined_df <- cbind(demo, extra_info)
combined_df[1, ]

3.2 Row binding with rbind()

Use rbind() to stack data frames vertically. The data frames must have the same column names and types.

# Extract one column from demo to create an additional data frame with the same structure (column names and types)
(new_participant <- demo[18,])
# Combine using rbind
extended_df <- rbind(demo, new_participant)
extended_df[nrow(extended_df),]

3.3 Merging with merge() (Join)

Use merge() to combine data frames based on a common column, similar to SQL joins (see figure below for a reminder on the different types of joins).

# Merge two data frames by participant ID `SEQN` (inner join by default)
merged_demo_bpx <- merge(demo, bpx, by = "SEQN")

# In base R, you can use the Reduce() function to iteratively merge a list of data frames
data_list <- list(demo, bpx, bmx) # list of data frames to merge
merged_demo_bpx_bmx <- Reduce(function(x, y) merge(x, y, by = "SEQN"), data_list) # perform an inner join on all data frames by 'SEQN'

You should specify the type of join you are looking for:

  • Inner join (default): keep only rows with matching SEQN in both data frames: inner_join_df <- merge(demo, bmx, by = "SEQN")
  • Left (outer) join: keep all rows from demo and only matching rows from bmx: left_join_df <- merge(demo, bmx, by = "SEQN", all.x = TRUE)
  • Right (outer) join: keep all rows from bmx and only matching rows from demo: left_join_df <- merge(demo, bmx, by = "SEQN", all.y = TRUE)
  • Full (outer) join: keep all rows from both demo and bmx, filling with NA where there are no matches: full_join_df <- merge(demo, bmx, by = "SEQN", all = TRUE)

💡 merge() in base R is flexible but can be a bit verbose. For simpler syntax, you can also use the dplyr package with left_join(), right_join(), inner_join(), and full_join().

3.4 Exercises

✏️ Exercise on the NHANES data sets n°4: merge the 4 data sets demo, bpx, bmx and smq into a single data set merged_nhanes by performing an inner join on the SEQN ID and using the dplyr package.

4 Saving data

You can save data sets in different formats, depending on how you want to use them later:

  • CSV – human-readable and widely supported (e.g. by Excel, Python, etc.)
  • RDS – R-specific format for saving a single R object (more compact than CSV, preserves data types)
  • RData – used to save multiple R objects into a single file

Let us save a data frame in all those different formats.

# Specify the directory for the data
directory <- "~/Documents/GitHub/rforphysicians/data_sets/"

# Save as CSV
write.csv(merged_demo_bpx_bmx, file = file.path(directory,"merged_demo_bpx_bmx.csv"), row.names = FALSE)

# Save as RDS (recommended for re-loading in R)
saveRDS(merged_demo_bpx_bmx, file = file.path(directory,"merged_demo_bpx_bmx.rds"))

# Save as RData (can contain multiple objects)
save(merged_demo_bpx_bmx, file = file.path(directory,"merged_demo_bpx_bmx.RData"))

💡 file.path() constructs the path to a file from components in a platform-independent way. It concatenates paths and filenames, and automatically uses the correct file separator (/ on Unix/macOS, \ on Windows), making your code more robust and portable.

💡 You can load these later using:

  • read.csv("merged_demo_bpx_bmx.csv")
  • readRDS("merged_demo_bpx_bmx.rds")
  • load("merged_demo_bpx_bmx.RData")

4.1 Exercises

✏️ Exercise on the NHANES data sets n°5: Save the data frame resulting from Exercise n°4 in your working directory in both .csv and .rds formats.

5 Solutions to the exercises

Please not that those are only examples, there are always many ways to solve the same task!

☑️ Exercise on the NHANES data sets n°1: If you have trouble importing the data sets into R, let me know, I’d be glad to help.

☑️ Exercise on the NHANES data sets n°2: Did you manage to select a specific column you were interested in? Were you able to check how many men and women are included in the data set? Here are a few examples of operations you can use to explore the data set.

# View the first few rows of the dataset
head(demo)
# Display the names of all columns
names(demo)
##  [1] "SEQN"     "SDDSRVYR" "RIDSTATR" "RIAGENDR" "RIDAGEYR" "RIDAGEMN"
##  [7] "RIDRETH1" "RIDRETH3" "RIDEXMON" "RIDEXAGY" "RIDEXAGM" "DMQMILIZ"
## [13] "DMQADFC"  "DMDBORN4" "DMDCITZN" "DMDYRSUS" "DMDEDUC3" "DMDEDUC2"
## [19] "DMDMARTL" "RIDEXPRG" "SIALANG"  "SIAPROXY" "SIAINTRP" "FIALANG" 
## [25] "FIAPROXY" "FIAINTRP" "MIALANG"  "MIAPROXY" "MIAINTRP" "AIALANGA"
## [31] "WTINT2YR" "WTMEC2YR" "SDMVPSU"  "SDMVSTRA" "INDHHIN2" "INDFMIN2"
## [37] "INDFMPIR" "DMDHHSIZ" "DMDFMSIZ" "DMDHHSZA" "DMDHHSZB" "DMDHHSZE"
## [43] "DMDHRGND" "DMDHRAGE" "DMDHRBR4" "DMDHREDU" "DMDHRMAR" "DMDHSEDU"
# View all unique values in the "AIALANGA" (Interview Language) column
unique(demo$AIALANGA)
## [1] "English"         NA                "Spanish"         "Asian languages"
# Count how many men and women are in the dataset
table(demo$RIAGENDR)
## 
## Female   Male 
##   4900   4856
# Get a quick statistical summary of a few columns
summary(demo[,c('RIDAGEYR','DMDHHSZA','DMDHRAGE')])
##     RIDAGEYR       DMDHHSZA        DMDHRAGE    
##  Min.   : 0.0   Min.   :0.000   Min.   :18.00  
##  1st Qu.: 9.0   1st Qu.:0.000   1st Qu.:33.00  
##  Median :26.0   Median :0.000   Median :43.00  
##  Mean   :31.4   Mean   :0.531   Mean   :45.39  
##  3rd Qu.:52.0   3rd Qu.:1.000   3rd Qu.:56.00  
##  Max.   :80.0   Max.   :3.000   Max.   :80.00
# View the number of missing values in each column
colSums(is.na(demo))
##     SEQN SDDSRVYR RIDSTATR RIAGENDR RIDAGEYR RIDAGEMN RIDRETH1 RIDRETH3 
##        0        0        0        0        0     9130        0        0 
## RIDEXMON RIDEXAGY RIDEXAGM DMQMILIZ  DMQADFC DMDBORN4 DMDCITZN DMDYRSUS 
##      418     6338     5747     3749     9205        0        5     7683 
## DMDEDUC3 DMDEDUC2 DMDMARTL RIDEXPRG  SIALANG SIAPROXY SIAINTRP  FIALANG 
##     7157     4196     4196     8548        0        6        0      105 
## FIAPROXY FIAINTRP  MIALANG MIAPROXY MIAINTRP AIALANGA WTINT2YR WTMEC2YR 
##      105      105     3043     3043     3043     4002        0        0 
##  SDMVPSU SDMVSTRA INDHHIN2 INDFMIN2 INDFMPIR DMDHHSIZ DMDFMSIZ DMDHHSZA 
##        0        0       81       51      840        0        0        0 
## DMDHHSZB DMDHHSZE DMDHRGND DMDHRAGE DMDHRBR4 DMDHREDU DMDHRMAR DMDHSEDU 
##        0        0        0        0      365      362      136     4881
# Calculate the average age
mean(demo$RIDAGEYR, na.rm = TRUE)
## [1] 31.40262

☑️ Exercise on the NHANES data sets n°3:

# Filter the dataset to include only female patients that are above 18 years old and that took the interview in Spanish.
demo_filtered <- demo[demo$RIAGENDR == "Female" & 
                      demo$RIDAGEYR > 17 & 
                      !is.na(demo$AIALANGA) & demo$AIALANGA == "Spanish", ]
ind <- c('RIAGENDR', 'RIDAGEYR', 'AIALANGA')
demo_filtered[, ind]

💡 Note: When filtering on a variable that contains missing values (e.g., AIALANGA), you must explicitly exclude NAs using !is.na(...). This is because comparisons like demo$AIALANGA == “Spanish” return NA for missing values, not FALSE, so those rows aren’t properly excluded from the subset.

☑️ Exercise on the NHANES data sets n°4:

# If necessary, install the dplyr package
install.packages("dplyr")
# Load the dplyr package
library(dplyr)

# Merge the datasets using inner joins by SEQN
data_list <- list(demo, bpx, bmx, smq)
merged_nhanes <- Reduce(function(x, y) inner_join(x, y, by = "SEQN"), data_list)

☑️ Exercise on the NHANES data sets n°5:

# Save the merged dataset in your working directory
# Click on Session > Set Working Directory > To Source File Location, or use file.path()
write.csv(merged_nhanes, "merged_nhanes.csv", row.names = FALSE)
saveRDS(merged_nhanes, "merged_nhanes.rds")

6 NHANES data sets

Here are listed some of the variables from the NHANES data sets.

6.1 Demographics (DEMO_G)

Variable Name Description
RIDAGEYR Participant’s age in years
RIAGENDR Participant’s gender
DMDHHSIZ Total number of people in the household
DMDHHSZA Number of children aged 5 or younger in the household
DMDHRAGE Age of the household reference person
DMDHRMAR Marital status of the household reference person
DMDHRGND Gender of the household reference person
AIALANGA Language of the interview

6.2 Blood Pressure (BPX_G)

Variable Name Description
BPXSY1 Systolic blood pressure (first reading) in mm Hg
BPXSY2 Systolic blood pressure (second reading) in mm Hg
BPXSY3 Systolic blood pressure (third reading) in mm Hg
BPXDI1 Diastolic blood pressure (first reading) in mm Hg
BPXDI2 Diastolic blood pressure (second reading) in mm Hg
BPXDI3 Diastolic blood pressure (third reading) in mm Hg
BPXPULS Pulse rate (beats per minute)
BPXPLS 60-second pulse (30-second pulse multiplied by 2)
BPXPTY Pulse type (e.g., regular or irregular)
BPXML1 Maximum inflation level (mm Hg)

6.3 Body Measures (BMX_G)

Variable Name Description
BMXWT Weight (kg)
BMXHT Standing height (cm)
BMXBMI Body Mass Index (kg/m²)
BMXWAIST Waist circumference (cm)
BMXHIP Hip circumference (cm)
BMXARML Upper arm length (cm)
BMXARMC Upper arm circumference (cm)
BMXLEG Upper leg length (cm)

6.4 Smoking Questionnaire (SMQ_G)

Variable Name Description
SMQ020 Smoked at least 100 cigarettes in life
SMQ040 Do you now smoke cigarettes?
SMQ050Q Average number of cigarettes smoked per day
SMD030 Age when first smoked cigarettes regularly
SMD070 Age when last smoked cigarettes regularly
SMQ680 Smoked cigars in the past 5 days
SMQ690 Smoked pipes in the past 5 days
SMQ700 Smoked chewing tobacco in the past 5 days
SMQ710 Smoked snuff in the past 5 days

References

Alexander Henzi. 2021. “Programming and Data Analysis with R.” Lecture notes.
Burns, Patrick. n.d. The R Inferno. Accessed May 8, 2025. https://www.burns-stat.com/documents/books/the-r-inferno/.
“ChatGPT.” n.d. Accessed January 26, 2025. https://chatgpt.com.
Christopher J. Endres. 2025. “Introducing nhanesA.” https://cran.r-project.org/web/packages/nhanesA/vignettes/Introducing_nhanesA.html.
“Create Elegant Data Visualisations Using the Grammar of Graphics.” n.d. Accessed January 26, 2025. https://ggplot2.tidyverse.org/.
David, Author. 2016. “BIRT Joins.” MBSE Chaos. https://mbsechaos.wordpress.com/2016/05/24/birt-joins/.
Elena Kosourova. n.d. “RStudio Tutorial for Beginners: A Complete Guide.” Accessed January 26, 2025. https://www.datacamp.com/tutorial/r-studio-tutorial.
Grolemund, Hadley Wickham and Garrett. n.d. R for Data Science. Accessed May 8, 2025. https://r4ds.had.co.nz/introduction.html.
Mayer, Michael. 2025. “Mayer79/Statistical_computing_material.” https://github.com/mayer79/statistical_computing_material.
Patrick Burns. n.d. Impatient R. Accessed May 8, 2025. https://www.burns-stat.com/documents/tutorials/impatient-r/.
“Synthetic Dataset for AI in Healthcare.” n.d. Accessed May 9, 2025. https://www.kaggle.com/datasets/smmmmmmmmmmmm/synthetic-dataset-for-ai-in-healthcare.
“The Comprehensive R Archive Network.” n.d. Accessed January 26, 2025. https://stat.ethz.ch/CRAN/.
W. N. Venables, D. M. Smith and the R Core Team. n.d. “An Introduction to R.” Accessed May 8, 2025. https://cran.r-project.org/doc/manuals/r-release/R-intro.html.
Wickham, Hadley. n.d. Advanced R. Accessed May 8, 2025. https://adv-r.hadley.nz/introduction.html.